Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8035
    Prev
    Next
    INDEX
    Explanations

    references to soy-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to soy products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.82
     Grateful
    -0.73
     Exile
    -0.71
     CBI
    -0.71
    hani
    -0.70
    umbnail
    -0.67
     Imran
    -0.67
    cffffcc
    -0.67
     McDonnell
    -0.66
     Represent
    -0.64
    POSITIVE LOGITS
    bean
    1.59
    beans
    1.57
    food
    0.96
    bowl
    0.92
     soy
    0.87
     sauce
    0.86
    wu
    0.82
    atown
    0.81
    char
    0.80
    ono
    0.80
    Activations Density 0.003%

    No Known Activations